Merge git://git.kernel.org/pub/scm/linux/kernel/git/davem/net

7 files changed, 50 insertions, 40 deletions

diff --git a/block/bio.c b/block/bio.c
index 71a78d9fb8b7..b64cedc7f87c 100644
--- a/block/bio.c
+++ b/block/bio.c
@@ -849,20 +849,14 @@ static int __bio_iov_bvec_add_pages(struct bio *bio, struct iov_iter *iter)
 	size = bio_add_page(bio, bv->bv_page, len,
 				bv->bv_offset + iter->iov_offset);
 	if (size == len) {
-		struct page *page;
-		int i;
+		if (!bio_flagged(bio, BIO_NO_PAGE_REF)) {
+			struct page *page;
+			int i;
+
+			mp_bvec_for_each_page(page, bv, i)
+				get_page(page);
+		}
 
-		/*
-		 * For the normal O_DIRECT case, we could skip grabbing this
-		 * reference and then not have to put them again when IO
-		 * completes. But this breaks some in-kernel users, like
-		 * splicing to/from a loop device, where we release the pipe
-		 * pages unconditionally. If we can fix that case, we can
-		 * get rid of the get here and the need to call
-		 * bio_release_pages() at IO completion time.
-		 */
-		mp_bvec_for_each_page(page, bv, i)
-			get_page(page);
 		iov_iter_advance(iter, size);
 		return 0;
 	}
@@ -925,10 +919,12 @@ static int __bio_iov_iter_get_pages(struct bio *bio, struct iov_iter *iter)
  * This takes either an iterator pointing to user memory, or one pointing to
  * kernel pages (BVEC iterator). If we're adding user pages, we pin them and
  * map them into the kernel. On IO completion, the caller should put those
- * pages. For now, when adding kernel pages, we still grab a reference to the
- * page. This isn't strictly needed for the common case, but some call paths
- * end up releasing pages from eg a pipe and we can't easily control these.
- * See comment in __bio_iov_bvec_add_pages().
+ * pages. If we're adding kernel pages, and the caller told us it's safe to
+ * do so, we just have to add the pages to the bio directly. We don't grab an
+ * extra reference to those pages (the user should already have that), and we
+ * don't put the page on IO completion. The caller needs to check if the bio is
+ * flagged BIO_NO_PAGE_REF on IO completion. If it isn't, then pages should be
+ * released.
  *
  * The function tries, but does not guarantee, to pin as many pages as
  * fit into the bio, or are requested in *iter, whatever is smaller. If
@@ -940,6 +936,13 @@ int bio_iov_iter_get_pages(struct bio *bio, struct iov_iter *iter)
 	const bool is_bvec = iov_iter_is_bvec(iter);
 	unsigned short orig_vcnt = bio->bi_vcnt;
 
+	/*
+	 * If this is a BVEC iter, then the pages are kernel pages. Don't
+	 * release them on IO completion, if the caller asked us to.
+	 */
+	if (is_bvec && iov_iter_bvec_no_ref(iter))
+		bio_set_flag(bio, BIO_NO_PAGE_REF);
+
 	do {
 		int ret;
 
@@ -1696,7 +1699,8 @@ static void bio_dirty_fn(struct work_struct *work)
 		next = bio->bi_private;
 
 		bio_set_pages_dirty(bio);
-		bio_release_pages(bio);
+		if (!bio_flagged(bio, BIO_NO_PAGE_REF))
+			bio_release_pages(bio);
 		bio_put(bio);
 	}
 }
@@ -1713,7 +1717,8 @@ void bio_check_pages_dirty(struct bio *bio)
 			goto defer;
 	}
 
-	bio_release_pages(bio);
+	if (!bio_flagged(bio, BIO_NO_PAGE_REF))
+		bio_release_pages(bio);
 	bio_put(bio);
 	return;
 defer:
diff --git a/block/blk-cgroup.c b/block/blk-cgroup.c
index 77f37ef8ef06..617a2b3f7582 100644
--- a/block/blk-cgroup.c
+++ b/block/blk-cgroup.c
@@ -1736,8 +1736,8 @@ out:
 
 /**
  * blkcg_schedule_throttle - this task needs to check for throttling
- * @q - the request queue IO was submitted on
- * @use_memdelay - do we charge this to memory delay for PSI
+ * @q: the request queue IO was submitted on
+ * @use_memdelay: do we charge this to memory delay for PSI
  *
  * This is called by the IO controller when we know there's delay accumulated
  * for the blkg for this task.  We do not pass the blkg because there are places
@@ -1769,8 +1769,9 @@ void blkcg_schedule_throttle(struct request_queue *q, bool use_memdelay)
 
 /**
  * blkcg_add_delay - add delay to this blkg
- * @now - the current time in nanoseconds
- * @delta - how many nanoseconds of delay to add
+ * @blkg: blkg of interest
+ * @now: the current time in nanoseconds
+ * @delta: how many nanoseconds of delay to add
  *
  * Charge @delta to the blkg's current delay accumulation.  This is used to
  * throttle tasks if an IO controller thinks we need more throttling.
diff --git a/block/blk-iolatency.c b/block/blk-iolatency.c
index 2620baa1f699..507212d75ee2 100644
--- a/block/blk-iolatency.c
+++ b/block/blk-iolatency.c
@@ -75,6 +75,7 @@
 #include <linux/blk-mq.h>
 #include "blk-rq-qos.h"
 #include "blk-stat.h"
+#include "blk.h"
 
 #define DEFAULT_SCALE_COOKIE 1000000U
 
diff --git a/block/blk-merge.c b/block/blk-merge.c
index 22467f475ab4..1c9d4f0f96ea 100644
--- a/block/blk-merge.c
+++ b/block/blk-merge.c
@@ -180,7 +180,7 @@ static unsigned get_max_segment_size(struct request_queue *q,
  */
 static bool bvec_split_segs(struct request_queue *q, struct bio_vec *bv,
 		unsigned *nsegs, unsigned *last_seg_size,
-		unsigned *front_seg_size, unsigned *sectors)
+		unsigned *front_seg_size, unsigned *sectors, unsigned max_segs)
 {
 	unsigned len = bv->bv_len;
 	unsigned total_len = 0;
@@ -190,7 +190,7 @@ static bool bvec_split_segs(struct request_queue *q, struct bio_vec *bv,
 	 * Multi-page bvec may be too big to hold in one segment, so the
 	 * current bvec has to be splitted as multiple segments.
 	 */
-	while (len && new_nsegs + *nsegs < queue_max_segments(q)) {
+	while (len && new_nsegs + *nsegs < max_segs) {
 		seg_size = get_max_segment_size(q, bv->bv_offset + total_len);
 		seg_size = min(seg_size, len);
 
@@ -240,6 +240,7 @@ static struct bio *blk_bio_segment_split(struct request_queue *q,
 	bool do_split = true;
 	struct bio *new = NULL;
 	const unsigned max_sectors = get_max_io_size(q, bio);
+	const unsigned max_segs = queue_max_segments(q);
 
 	bio_for_each_bvec(bv, bio, iter) {
 		/*
@@ -254,14 +255,14 @@ static struct bio *blk_bio_segment_split(struct request_queue *q,
 			 * Consider this a new segment if we're splitting in
 			 * the middle of this vector.
 			 */
-			if (nsegs < queue_max_segments(q) &&
+			if (nsegs < max_segs &&
 			    sectors < max_sectors) {
 				/* split in the middle of bvec */
 				bv.bv_len = (max_sectors - sectors) << 9;
 				bvec_split_segs(q, &bv, &nsegs,
 						&seg_size,
 						&front_seg_size,
-						&sectors);
+						&sectors, max_segs);
 			}
 			goto split;
 		}
@@ -283,7 +284,7 @@ static struct bio *blk_bio_segment_split(struct request_queue *q,
 			continue;
 		}
 new_segment:
-		if (nsegs == queue_max_segments(q))
+		if (nsegs == max_segs)
 			goto split;
 
 		bvprv = bv;
@@ -296,7 +297,7 @@ new_segment:
 			if (nsegs == 1 && seg_size > front_seg_size)
 				front_seg_size = seg_size;
 		} else if (bvec_split_segs(q, &bv, &nsegs, &seg_size,
-				    &front_seg_size, &sectors)) {
+				    &front_seg_size, &sectors, max_segs)) {
 			goto split;
 		}
 	}
@@ -415,7 +416,7 @@ new_segment:
 			bvprv = bv;
 			prev = 1;
 			bvec_split_segs(q, &bv, &nr_phys_segs, &seg_size,
-					&front_seg_size, NULL);
+					&front_seg_size, NULL, UINT_MAX);
 		}
 		bbio = bio;
 	}
diff --git a/block/blk-mq.c b/block/blk-mq.c
index a9c181603cbd..70b210a308c4 100644
--- a/block/blk-mq.c
+++ b/block/blk-mq.c
@@ -782,7 +782,6 @@ void blk_mq_add_to_requeue_list(struct request *rq, bool at_head,
 	if (kick_requeue_list)
 		blk_mq_kick_requeue_list(q);
 }
-EXPORT_SYMBOL(blk_mq_add_to_requeue_list);
 
 void blk_mq_kick_requeue_list(struct request_queue *q)
 {
@@ -1093,8 +1092,7 @@ static bool blk_mq_mark_tag_wait(struct blk_mq_hw_ctx *hctx,
 	bool ret;
 
 	if (!(hctx->flags & BLK_MQ_F_TAG_SHARED)) {
-		if (!test_bit(BLK_MQ_S_SCHED_RESTART, &hctx->state))
-			set_bit(BLK_MQ_S_SCHED_RESTART, &hctx->state);
+		blk_mq_sched_mark_restart_hctx(hctx);
 
 		/*
 		 * It's possible that a tag was freed in the window between the
@@ -2857,7 +2855,7 @@ struct request_queue *blk_mq_init_allocated_queue(struct blk_mq_tag_set *set,
 	/*
 	 * Default to classic polling
 	 */
-	q->poll_nsec = -1;
+	q->poll_nsec = BLK_MQ_POLL_CLASSIC;
 
 	blk_mq_init_cpu_queues(q, set->nr_hw_queues);
 	blk_mq_add_queue_tag_set(set, q);
@@ -3392,7 +3390,7 @@ static bool blk_mq_poll_hybrid(struct request_queue *q,
 {
 	struct request *rq;
 
-	if (q->poll_nsec == -1)
+	if (q->poll_nsec == BLK_MQ_POLL_CLASSIC)
 		return false;
 
 	if (!blk_qc_t_is_internal(cookie))
diff --git a/block/blk-mq.h b/block/blk-mq.h
index c11353a3749d..0ed8e5a8729f 100644
--- a/block/blk-mq.h
+++ b/block/blk-mq.h
@@ -41,6 +41,8 @@ void blk_mq_free_queue(struct request_queue *q);
 int blk_mq_update_nr_requests(struct request_queue *q, unsigned int nr);
 void blk_mq_wake_waiters(struct request_queue *q);
 bool blk_mq_dispatch_rq_list(struct request_queue *, struct list_head *, bool);
+void blk_mq_add_to_requeue_list(struct request *rq, bool at_head,
+				bool kick_requeue_list);
 void blk_mq_flush_busy_ctxs(struct blk_mq_hw_ctx *hctx, struct list_head *list);
 bool blk_mq_get_driver_tag(struct request *rq);
 struct request *blk_mq_dequeue_from_ctx(struct blk_mq_hw_ctx *hctx,
diff --git a/block/blk-sysfs.c b/block/blk-sysfs.c
index 59685918167e..422327089e0f 100644
--- a/block/blk-sysfs.c
+++ b/block/blk-sysfs.c
@@ -360,8 +360,8 @@ static ssize_t queue_poll_delay_show(struct request_queue *q, char *page)
 {
 	int val;
 
-	if (q->poll_nsec == -1)
-		val = -1;
+	if (q->poll_nsec == BLK_MQ_POLL_CLASSIC)
+		val = BLK_MQ_POLL_CLASSIC;
 	else
 		val = q->poll_nsec / 1000;
 
@@ -380,10 +380,12 @@ static ssize_t queue_poll_delay_store(struct request_queue *q, const char *page,
 	if (err < 0)
 		return err;
 
-	if (val == -1)
-		q->poll_nsec = -1;
-	else
+	if (val == BLK_MQ_POLL_CLASSIC)
+		q->poll_nsec = BLK_MQ_POLL_CLASSIC;
+	else if (val >= 0)
 		q->poll_nsec = val * 1000;
+	else
+		return -EINVAL;
 
 	return count;
 }